Data-driven modeling and online algorithm for hot rolling process

Based on the idea that the accuracy of model could be significantly improved by combing several sub-models, a multiple support vector machine (MSVM) modeling approach is proposed to build the strip thickness model in hot rolling Automatic Gauge Control (AGC) system. The subtractive clustering is adopted to divide the input space into several clusters, and each cluster subset is built by Least-square support vector machine. Then when the online data constantly increased, the clustering subset is updated on-line by subtractive clustering algorithm, and the parameter of each local model is updated by the recursion algorithm. The results of experiment demonstrate the method the effectiveness of the proposed modeling approach, and it has powerful ability of online learning.